Introduction

The hidden Markov model (HMM) is a very powerful statistical method of characterizing the observed data samples of a discrete-time series. Not only can it provide an efficient way to build parsimonious parametric models, it can also incorporate the dynamic programming principle in its core for a unified pattern segmentation and pattern classification of time-varying data sequences. The data samples in the time series can be discretely or continuously distributed; they can be scalars or vectors. The underlying assumption of the HMM is the the data samples can be well characterized as a parametric random process, and the parameters of the stochastic process can be estimated in a precise and well-defined framework.